Disclosed is an image segmentation device. The image segmentation device may include: a storage unit storing a segmentation model learned so as to segment at least one predetermined object; and at least one processor inputting input data into the segmentation model and segmenting at least one predetermined object in the input data, in which the segmentation model may include an encoder including at least one dimension reduction block reducing a dimension of the input data, a decoder including at least one dimension increase block increasing the dimension of output data output from the encoder by using data output from at least one dimension reduction block, and an auxiliary classification model receiving the output data and recognizing whether a specific object is included in the output data.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The image segmentation device of claim 1, wherein the learning images include at least one patch acquired by randomly cropping an image labeled with each of the at least one predetermined object.
3. The image segmentation device of claim 1, wherein a final output end of the decoder further includes a boundary refine module adjusting a final feature map inputted into a final classification operation so that a boundary for area segmentation related to each of the at least one predetermined object is refined.
4. The image segmentation device of claim 3, wherein the final classification operation includes an operation through at least one convolutional layer and a Softmax activation function.
5. The image segmentation device of claim 3, wherein the boundary refine module has a residual block structure.
6. The image segmentation device of claim 1, wherein the at least one dimension reduction block and the at least one dimension increase block include a multi-scale dilated residual block having a plurality of convolutional layers having different dilation rates arranged in parallel and including a residual connection.
7. The image segmentation device of claim 1, wherein dimension reduction block disposed on a final layer among the at least one dimension reduction block includes a dropout layer for preventing overfitting.
8. The image segmentation device of claim 1, wherein the processor performs 3D rendering by using final data outputted by inputting the input data into the segmentation model, and the input data.
9. The image segmentation device of claim 1, wherein the auxiliary classification model receives the output data output from a bottleneck block of the encoder.
10. The image segmentation device of claim 1, wherein the processor generates a graph so as to perform quantitative measurement and comparison for a degree of newborn membrane proliferation of implanted biodegradable stents.
11. The image segmentation device of claim 1, wherein the specific object comprises a strut of a biodegradable stent.
12. The image segmentation device of claim 1, wherein the specific object comprises a tissue.
13. The image segmentation device of claim 1, wherein the learning images comprise at least one patch acquired by random crop of an image labeled with the at least one predetermined object.
14. The image segmentation device of claim 13, wherein the auxiliary classification model is learned whether the specific object is included in a random cropped patch.
15. The image segmentation device of claim 1, wherein the loss function L is calculated using a cross entropy term for the binary classification result of the auxiliary classification model.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 15, 2022
April 30, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.